| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011624527753560012, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011624527753560012, | |
| "grad_norm": 0.5896633863449097, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6775, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011624527753560012, | |
| "eval_loss": 0.6523699164390564, | |
| "eval_runtime": 18.9491, | |
| "eval_samples_per_second": 19.157, | |
| "eval_steps_per_second": 9.605, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023249055507120024, | |
| "grad_norm": 0.7550370097160339, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5538, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0034873583260680036, | |
| "grad_norm": 0.9095613956451416, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6648, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0034873583260680036, | |
| "eval_loss": 0.6497126817703247, | |
| "eval_runtime": 17.0378, | |
| "eval_samples_per_second": 21.306, | |
| "eval_steps_per_second": 10.682, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004649811101424005, | |
| "grad_norm": 0.9829018712043762, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6723, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005812263876780006, | |
| "grad_norm": 0.6747056245803833, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6645, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006974716652136007, | |
| "grad_norm": 0.717897891998291, | |
| "learning_rate": 0.00012, | |
| "loss": 0.5416, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006974716652136007, | |
| "eval_loss": 0.602017343044281, | |
| "eval_runtime": 17.0249, | |
| "eval_samples_per_second": 21.322, | |
| "eval_steps_per_second": 10.69, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008137169427492008, | |
| "grad_norm": 0.8567973375320435, | |
| "learning_rate": 0.00014, | |
| "loss": 0.701, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00929962220284801, | |
| "grad_norm": 0.6242435574531555, | |
| "learning_rate": 0.00016, | |
| "loss": 0.5408, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010462074978204011, | |
| "grad_norm": 0.5915112495422363, | |
| "learning_rate": 0.00018, | |
| "loss": 0.5469, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010462074978204011, | |
| "eval_loss": 0.4810210168361664, | |
| "eval_runtime": 17.0883, | |
| "eval_samples_per_second": 21.243, | |
| "eval_steps_per_second": 10.651, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011624527753560012, | |
| "grad_norm": 0.5937075614929199, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5251, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2959302797033472.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |